Object Tracking Benchmark

TLDR

Object tracking is a central computer vision task with many algorithms, yet existing evaluation sequences are often biased, lack common ground‑truth, and use inconsistent initialization, making quantitative comparisons unreliable. This study aims to evaluate state‑of‑the‑art online tracking algorithms within a unified framework to assess their relative performance. The authors built a large dataset with ground‑truth positions and attributes, integrated 31 public trackers into a common library, and evaluated them on 100 sequences under varied initialization settings. The analysis highlights robust tracking approaches and outlines promising directions for future research.

Abstract

Object tracking has been one of the most important and active research areas in the field of computer vision. A large number of tracking algorithms have been proposed in recent years with demonstrated success. However, the set of sequences used for evaluation is often not sufficient or is sometimes biased for certain types of algorithms. Many datasets do not have common ground-truth object positions or extents, and this makes comparisons among the reported quantitative results difficult. In addition, the initial conditions or parameters of the evaluated tracking algorithms are not the same, and thus, the quantitative results reported in literature are incomparable or sometimes contradictory. To address these issues, we carry out an extensive evaluation of the state-of-the-art online object-tracking algorithms with various evaluation criteria to understand how these methods perform within the same framework. In this work, we first construct a large dataset with ground-truth object positions and extents for tracking and introduce the sequence attributes for the performance analysis. Second, we integrate most of the publicly available trackers into one code library with uniform input and output formats to facilitate large-scale performance evaluation. Third, we extensively evaluate the performance of 31 algorithms on 100 sequences with different initialization settings. By analyzing the quantitative results, we identify effective approaches for robust tracking and provide potential future research directions in this field.